FedLossMix: A Loss-Based Adaptive Federated Learning Approach for Credit Scoring | IJCT Volume 13 – Issue 4 | IJCT-V13I4P10
International Journal of Computer Techniques
ISSN 2394-2231
Author
Anandadeep Balaa, Sibanjan Debeeprasad Dasb
Abstract
This study aims to address the challenge of systemic financial risk mitigation by improving credit scoring models trained under privacy constraints. It introduces Federated Loss-Based Mixing (FedLossMix) which is an adaptive Federated Learning (FL) aggregation method designed to handle data heterogeneity and class imbalance across financial institutions. The research develops an adaptive aggregation strategy that assigns dynamic weights to client model updates based on local validation loss. The method is evaluated using multiple heterogeneous credit risk datasets within a federated environment and compares its performance to traditional FL aggregation techniques such as FedAvg. FedLossMix demonstrates superior convergence stability and improved representational fairness across non-IID and imbalanced financial datasets. Experimental results show that the proposed approach consistently outperforms conventional FL aggregation methods in predicting borrower default probabilities. The proposed FedLossMix framework provides a robust and equitable way to collaboratively train Federated Learning (FL) models without sharing sensitive data. This method mitigates data-sharing and privacy risks by enabling better model performance under heterogeneous data conditions without requiring data centralization.
Keywords
Federated Learning, Artificial Intelligence, Machine Learning, Distributed Systems, Credit Risk Management
Conclusion
The research introduces the concept of FedLossMix, a federated learning framework designed to address the challenges of heterogeneous and imbalanced data. Federated Learning enables financial institutions to collaboratively train models while ensuring data privacy and regulatory compliance. However, traditional FL aggregation methods, such as FedAvg, FedProx, and Client-K Aggregation, fail to address the impact of heterogeneity in datasets and class imbalance on model performance. To overcome these challenges, FedLossMix dynamically assigns aggregation weights based on client validation loss, prioritizing contributions from well-generalized models while retaining proportional participation from all clients. Unlike existing approaches that rely on uniform constraints or hard client selection, this loss-based weighting mechanism enhances the stability and fairness of federated credit scoring models while reducing the computational overhead associated with knowledge distillation-based techniques like FedCodl and FedKT.
Experimental results across four credit scoring datasets demonstrate that FedLossMix consistently outperforms existing FL methods in terms of classification accuracy, F1-score, and convergence speed. The approach shows significant improvements in handling imbalanced credit data, mitigating biases in model aggregation while ensuring faster convergence and reduced communication overhead. Compared to baseline methods, FedLossMix offers more effective adaptation to heterogeneous financial datasets, leading to improved generalization and robustness in federated ML use cases such as credit scoring.
References
Ala’raj, Maher, and Maysam F Abbod. 2016. “Classifiers consensus system approach for credit scoring.” Knowledge-Based Systems 104: 89–105.
AI, N., 2023. Artificial intelligence risk management framework (AI RMF 1.0). URL: https://nvlpubs. nist. gov/nistpubs/ai/nist. ai, pp.100-1.
Ali, A., Abd Razak, S., Othman, S.H., Eisa, T.A.E., Al-Dhaqm, A., Nasser, M., Elhassan, T., Elshafie, H. and Saif, A., 2022. Financial fraud detection based on machine learning: a systematic literature review. Applied Sciences, 12(19), p.9637.
Banabilah, S., Aloqaily, M., Alsayed, E., Malik, N. and Jararweh, Y., 2022. Federated learning review: Fundamentals, enabling technologies, and future applications. Information processing & management, 59(6), p.103061.
Baesens, Bart, and Kristien Smedts. 2023. “Boosting credit risk models.” The British Accounting Review 101241.
Bharati, Subrato, M Rubaiyat Hossain Mondal, Prajoy Podder, and VB Surya Prasath. 2022. “Federated learning: Applications, challenges and future directions.” International Journal of Hybrid Intelligent Systems 18 (1-2): 19–35.
Chen, Ting-Hsuan, Chien-Chiang Lee, and Chung-Hua Shen. 2022. “Liquidity indicators, early warning signals in banks, and financial crises.” The North American Journal of Economics and Finance 62: 101732.
Chen, H., Zhu, T., Zhang, T., Zhou, W. and Yu, P.S., 2023. Privacy and fairness in federated learning: On the perspective of tradeoff. ACM Computing Surveys, 56(2), pp.1-37.
Act, E.A.I., 2024. The eu artificial intelligence act. European Union.
Dai, Y., Chen, Z., Li, J., Heinecke, S., Sun, L. and Xu, R., 2023, June. Tackling data heterogeneity in federated learning with class prototypes. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 6, pp. 7314-7322).
El Ouadrhiri, A. and Abdelhadi, A., 2022. Differential privacy for deep and federated learning: A survey. IEEE access, 10, pp.22359-22380. Gao, W. and Zhou, Z.H., 2020. Towards convergence rate analysis of random forests for classification. Advances in neural information processing systems, 33, pp.9300-9311.
Gou, Jianping, Baosheng Yu, Stephen J Maybank, and Dacheng Tao. 2021. “Knowledge distillation: A survey.” International Journal of Computer Vision 129 (6): 1789–1819.
Guembe, Blessing, Ambrose Azeta, Victor Osamor, and Raphael Ekpo. 2023. “A Federated Machine Learning Approaches For Anti-Money Laundering Detection.” Available at SSRN 4669561 .
Hand, David J, and William E Henley. 1997. “Statistical classification methods in consumer credit scoring: a review.” Journal of the Royal Statistical Society: Series A (Statistics in Society) 160 (3):
523–541.
He, Hongliang, Wenyu Zhang, and Shuai Zhang. 2018. “A novel ensemble method for credit scoring: Adaption of different imbalance ratios.” Expert Systems with Applications 98: 105–117.
Hilal, Anwer Mustafa, Shaha Al-Otaibi, Hany Mahgoub, Fahd N Al-Wesabi, Ghadah Aldehim, Abdelwahed Motwakel, Mohammed Rizwanullah, and Ishfaq Yaseen. 2023. “Deep learning enabled class imbalance with sand piper optimization based intrusion detection for secure cyber physical systems.” Cluster Computing 26 (3): 2085–2098.
Haddadpour, F. and Mahdavi, M., 2019. On the convergence of local descent methods in federated learning. arXiv preprint arXiv:1910.14425.
Ileberi, Emmanuel, Yanxia Sun, and Zenghui Wang. 2021. “Performance evaluation of machine learning methods for credit card fraud detection using SMOTE and AdaBoost.” IEEE Access 9: 165286– 165294.
Kawa, Deep, Sunaina Punyani, Priya Nayak, Arpita Karkera, and Varshapriya Jyotinagar. 2019. “Credit risk assessment from combined bank records using federated learning.” International Research Journal of Engineering and Technology (IRJET) 6 (4): 1355–1358.
Khandani, Amir E, Adlar J Kim, and Andrew W Lo. 2010. “Consumer credit-risk models via machinelearning algorithms.” Journal of Banking & Finance 34 (11): 2767–2787.
Kweon, Yonghyeon, Bingrong Sun, and B Brian Park. 2021. “Preserving privacy with federated learning in route choice behavior modeling.” Transportation research record 2675 (10): 268–276.
Kwon, S., Jang, J. and Kim, C.O., 2025. Credit scoring using multi-task Siamese neural network for improving prediction performance and stability. Expert Systems with Applications, 259, p.125327.
Lawlor-Forsyth, Erin, and M Michelle Gallant. 2018. “Financial institutions and money laundering: A threatening relationship?” Journal of Banking Regulation 19 (2): 131–148.
Li, Tian, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. “Federated optimization in heterogeneous networks.” Proceedings of Machine learning and systems 2: 429–450.
Lipton, Z.C., Elkan, C. and Naryanaswamy, B., 2014, September. Optimal thresholding of classifiers to maximize F1 measure. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 225-239). Berlin, Heidelberg: Springer Berlin Heidelberg.
Lu, Z., Pan, H., Dai, Y., Si, X. and Zhang, Y., 2024. Federated learning with non-iid data: A survey. IEEE Internet of Things Journal, 11(11), pp.19188-19209.
Marcolla, C., Sucasas, V., Manzano, M., Bassoli, R., Fitzek, F.H. and Aaraj, N., 2022. Survey on fully homomorphic encryption, theory, and applications. Proceedings of the IEEE, 110(10), pp.1572-1609.
Mammen, Priyanka Mary. 2021. “Federated learning: Opportunities and challenges.” arXiv preprint arXiv:2101.05428 .
McMahan, Brendan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. “Communication-efficient learning of deep networks from decentralized data.” In Artificial intelligence and statistics, 1273–1282. PMLR.
Moscato, Vincenzo, Antonio Picariello, and Giancarlo Sperlí. 2021. “A benchmark of machine learning approaches for credit score prediction.” Expert Systems with Applications 165: 113986.
Myalil, Delton, MA Rajan, Manoj Apte, and Sachin Lodha. 2021. “Robust collaborative fraudulent transaction detection using federated learning.” In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), 373–378. IEEE.
Ni, Xuanming, Xinyuan Shen, and Huimin Zhao. 2022. “Federated optimization via knowledge codistillation.” Expert Systems with Applications 191: 116310.
Pei, J., Liu, W., Li, J., Wang, L. and Liu, C., 2024. A review of federated learning methods in heterogeneous scenarios. IEEE Transactions on Consumer Electronics, 70(3), pp.5983-5999.
Reurink, Arjan. 2018. “Financial fraud: A literature review.” Journal of Economic Surveys 32 (5): 1292–1325.
Scott, A. O., Amajuoyi, P., & Adeusi, K. B. (2024). Effective credit risk mitigation strategies: Solutions for reducing exposure in financial institutions. Magna Scientia Advanced Research and Reviews, 11(1), 198-211.
Song, Yu, Yuyan Wang, Xin Ye, Russell Zaretzki, and Chuanren Liu. 2023. “Loan default prediction using a credit rating-specific and multi-objective ensemble learning scheme.” Information Sciences 629: 599–617.
Šušteršic, Maja, Dušan Mramor, and Jure Zupan. 2009. “Consumer credit scoring models with limitedˇ data.” Expert Systems with Applications 36 (3): 4736–4744.
Suvarna, R, and A Meena Kowshalya. 2020. “Credit card fraud detection using federated learning techniques.” International Journal of Scientific Research in Science, Engineering and Technology 7
(3).
Tian, Ye, Bo Bian, Xiaofei Tang, and Jing Zhou. 2021. “A new non-kernel quadratic surface approach for imbalanced data classification in online credit scoring.” Information Sciences 563: 150–165.
Tripathi, Diwakar, Alok Kumar Shukla, B Ramachandra Reddy, Ghanshyam S Bopche, and D Chandramohan. 2022. “Credit scoring models using ensemble learning and classification approaches: a comprehensive survey.” Wireless Personal Communications 123 (1): 785–812.
Truong, Nguyen, Kai Sun, Siyao Wang, Florian Guitton, and YiKe Guo. 2021. “Privacy preservation in federated learning: An insightful survey from the GDPR perspective.” Computers & Security 110: 102402.
Vettoruzzo, A., Bouguelia, M.R., Vanschoren, J., Rögnvaldsson, T. and Santosh, K.C., 2024. Advances and challenges in meta-learning: A technical review. IEEE transactions on pattern analysis and machine intelligence, 46(7), pp.4763-4779.
Wang, Zhongyi, Jin Xiao, Lu Wang, and Jianrong Yao. 2024. “A novel federated learning approach with knowledge transfer for credit scoring.” Decision Support Systems 177: 114084.
Xia, Yufei, Chuanzhe Liu, Bowen Da, and Fangming Xie. 2018. “A novel heterogeneous ensemble credit scoring model based on bstacking approach.” Expert Systems with Applications 93: 182–199.
Yang, Miao, Hua Qian, Ximin Wang, Yong Zhou, and Hongbin Zhu. 2021a. “Client selection for federated learning with label noise.” IEEE Transactions on Vehicular Technology 71 (2): 2193– 2197.
Yang, Wei, Yuan Yang, Xiaobing Dang, Hao Jiang, Yizhe Zhang, and Wei Xiang. 2021b. “A novel adaptive gradient compression approach for communication-efficient Federated Learning.” In 2021 China Automation Congress (CAC), 674–678. IEEE.
Yang, Wensi, Yuhang Zhang, Kejiang Ye, Li Li, and Cheng-Zhong Xu. 2019. “Ffd: A federated learning based method for credit card fraud detection.” In Big Data–BigData 2019: 8th International Congress, Held as Part of the Services Conference Federation, SCF 2019, San Diego, CA, USA, June 25–30, 2019, Proceedings 8, 18–32. Springer.
Zhang, Xiaoming, and Lean Yu. 2024. “Consumer credit risk assessment: A review from the state-ofthe-art classification algorithms, data traits, and learning methods.” Expert Systems with Applications 237: 121484.
Zhao, Yue, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra. 2018. “Federated learning with non-iid data.” arXiv preprint arXiv:1806.00582 .
Zhu, Zhuangdi, Junyuan Hong, and Jiayu Zhou. 2021. “Data-free knowledge distillation for heterogeneous federated learning.” In International conference on machine learning, 12878–12889. PMLR.
How to Cite This Paper
Anandadeep Balaa, Sibanjan Debeeprasad Dasb (2026). FedLossMix: A Loss-Based Adaptive Federated Learning Approach for Credit Scoring. International Journal of Computer Techniques, 13(4). ISSN: 2394-2231.
Related Posts:
